Deep Ensemble for the Recognition of Malignancy is a UKCA Class IIa AI as a Medical Device (AIaMD) that assesses dermoscopic images of skin lesions for skin cancer. See our most recent DERM performance analysis here.
Watch a video explaining DERM and how it works.
Currently DERM is mainly deployed in the patient pathway following an urgent suspected skin cancer referral by an NHS GP for suspicion of skin cancer. In the post referral pathway, DERM is deployed within an imaging clinic prior to attending a dermatologist appointment. Typically only between 6-8% of urgent suspected skin cancer referrals are malignant and DERM is used to ensure the malignant lesions are seen by consultant dermatologists faster while benign lesions can be sent down other appropriate pathways.
We have now assessed a significant number of patients and DERM has correctly identified more than 8,000 cancers. An NHSE-commissioned independent evaluation found that DERM performance is at least as good as dermatologists. See our latest performance analysis here.
In the majority of deployments DERM is deployed to assess patients after they have been referred by their GP. In our most recent performance report (Q2 2024), we saw that the DERM Secondary Care pathways have increased the likelihood that dermatologists are seeing patients who actually have skin cancer by 19-67%.
Combined with use of the Skin Analytics teledermatology platform, our NHS Secondary Care partners remove the need for up to 95% of face-to-face urgent suspected skin cancer appointments.
Since 2018, we have worked with teams from Health Enterprise East, the York Health Economics Consortium, Imperial Trust, as well as the Exeter Test Group to ensure that our services are truly sustainable for the NHS.
We have now had three independent evaluations demonstrating around £2 benefits for every £1 spent on our pathways, which reinforces the results seen in our own health economic analyses which show that Skin Analytics delivers robust NHS dermatology cost savings.
Skin Analytics are committed to ensuring we are helping to provide sustainable solutions for skin cancer.
In addition to the data we publish, much of which has been externally audited, Skin Analytics is working with a number of external partners to evaluate and support the expansion of our services across the NHS. An example of some of this work is outlined below.
NHSE’s Outpatient Recovery and Transformation Programme (OPRT) team commissioned Edge Health to write an independent report evaluating the use of AI in skin cancer pathways. Edge Health were tasked with exploring all AI technologies with appropriate regulatory clearance to be deployed within autonomous pathways. DERM was the only technology that met the requirements, so much of the report focuses on our performance. They found that AIaMD can be used autonomously in the NHS if certified under classes UKCA IIa or CE III. DERM is the only AIaMD with the necessary evidence base demonstrating its safety and effectiveness for regulatory approval at this level. The evaluation also showed that DERM’s performance is at least as good as face-to-face dermatologist evaluations. The Negative Predictive Value (NPV) for correctly excluding melanoma in a matched-prevalence population were 99.8% for DERM and 98.9% for dermatologists.
In a separate evaluation, Edge Health worked on behalf of the East Midlands Academic Health Science Network to evaluate our pathway at University Hospitals Leicester. They found that despite being in its pilot phase, the AI tool demonstrated its capability to enhance patient access to dermatology services. In addition, they found that the pathway could offer considerable benefits to the wider Dermatology cohort, healthcare staff, and the health system if implemented at scale, with potential yearly savings across the Midlands ranging between £2.1M and £5.7M.
The Department of Health and Social Care (DHSC) funded deployment and a real-world evaluation of DERM as part of the AI in Health and Care Award. The evaluation conducted by University of Surrey and Unity Insights found that in secondary care, DERM demonstrated high pathway sensitivity for malignant melanoma (97%) and effectively triages high risk lesions to the appropriate management outcome. Health economics compared teledermatology both with and without DERM against face-to-face referrals – all instances highlighted savings for the NHS.
More on our independent evaluations here.
DERM has been deployed since 2020 and over this time we have been monitoring post-deployment performance as part of our post market surveillance. Over this time we have seen over 120,000 patients in our NHS pathways and have demonstrated that our services are accessible to patients from a wide range of ages (18-100) and all skin types (Fitzpatrick I-VI).
It is well recognised that skin cancer is more prevalent in lighter skin types and so this is also reflected in the patient population which we have seen presented to our pathways. 3% of cases NHS organisations have seen with the Skin Analytics platform have been recorded as having Fitzpatrick type V/VI skin.
For these patients, we have correctly identified all melanoma, SCCs and BCCs and DERM performance is in line with our targets but the numbers are too low to report. We continue to monitor this closely with our NHS partners and are committed to building a solution for all patients.
More here.
DERM assessments do not discriminate – they are based on dermoscopic image alone and no demographic factors are taken into account. If for any reason the characteristics of a particular mole or lesion render it not suitable for assessment by DERM (e.g. it is ulcerated or under the nails), the patient’s case is automatically routed to a dermatologist assessment, ensuring timely and uncompromised access to care. Across all protected groups, speed of access to care would be increased due to reduced waiting times relative to dermatologist appointments.
We recognise the anxiety felt when using technology on under-represented groups and take this very seriously. To ensure we provide – and can monitor – a service that is safe and efficient for all patients, we always conduct sub-group analyses making sure we understand how our pathways are impacting patients from all backgrounds.
We have completed and regularly update our NHS England and NHS Improvement (NHSEI): Equality and Health Inequalities Impact Assessment (EHIA). Download an overview of our EHIA or learn more on our equality of access page.
DERM itself only accesses dermoscopic images of skin lesions, and doesn’t have any access to patient data. The Skin Analytics teledermatology platform that facilitates data capture from patients has been built with GDPR principles in mind. All data is stored in the UK, with security measures validated by annual penetration testing and reinforced by our ISO 27001 certification, our NHS DSP Toolkit conformance and our NHS Cybersecurity Essentials certification.
AI used in skin cancer pathways are medical devices governed by law under The UK Medical Device Regulations 2002 (“UK MDR”) which is overseen by the MHRA, the UK’s medicines and healthcare products regulatory agency.
DERM has the required UKCA mark as a Class IIa medical device under UK law and remains the only approved Class IIa device for assessing skin cancer.
Medical device regulation requires that manufacturers like Skin Analytics identify the benefits and risks to patients and provide sufficient evidence that residual risks are sufficiently low and outweighed by the benefits of the medical device.
The classification of medical devices under the UK MDR is a risk-based system taking into account the intended use and potential risks associated with a medical device. This approach uses a set of ‘classification rules’ to determine the appropriate classification for a device and, in turn, indicate the level of regulatory control and oversight required for the device.
Our AI product is classified as a Class IIa medical device. This means that our device is required to undergo a comprehensive quality and technical assessment by an independent body appointed by the MHRA to determine whether the device is compliant with the UK MDR. A key component of this assessment is the independent review of our Clinical Evaluation Report (“CER”).
The CER is a report that identifies, appraises and evaluates clinical evidence for a device in order to verify the safety and performance, including clinical benefits, of the device when used as intended. Skin Analytics has successfully completed this rigorous assessment and our device remains the only Class IIa approved AI medical device in dermatology.
Securing a Class IIa medical device approval is not a milestone, it is a commitment to continue to operate an effective quality management system that is evaluated against the best in class standards agreed by regulatory bodies.
That means that we are constantly working to maintain our medical device and operate safe and effective processes. It is a living process and one in which we are constantly looking for improvement.
AI as a medical device should be held to high standards and that is what the regulatory requirements do both with respect to clinical evidence and as importantly the quality and safety systems a company operates.
No, DERM does not self learn and while we continually improve our models and performance these are manually released following the appropriate regulatory pathway to ensure the appropriate verification and validation before release.
